Email this article Methodology for identifying and ranking road traffic accident hotspots based on spatial analysis and program-targeted approach
- Authors: Zagorodnikh N.A.1, Konstantinov I.S.2
-
Affiliations:
- MIREA – Russian Technological University
- Belgorod State Technological University named after V.G. Shukhov
- Issue: Vol 12, No 5 (2025)
- Pages: 11-28
- Section: SYSTEM ANALYSIS, INFORMATION MANAGEMENT AND PROCESSING, STATISTICS
- URL: https://bakhtiniada.ru/2313-223X/article/view/358381
- DOI: https://doi.org/10.33693/2313-223X-2025-12-5-11-28
- EDN: https://elibrary.ru/EEQEAQ
- ID: 358381
Cite item
Open Access
Access granted
Subscription Access
Abstract
The article proposes an enhancement of an information system for analyzing road traffic accident hotspots (RTAs), developed within the framework of a program-targeted approach and geoinformation technologies. The system’s architecture is described, including spatial analysis algorithms, methods for identifying and consolidating clusters, as well as mechanisms for formalized accident representation. Special attention is given to the implementation of accident hotspot prioritization based on risk factors, recommended measures, and the expected mitigation effect. Verification was conducted using real-world urban accident data. The proposed solution demonstrates the stability of the implemented algorithms and their applicability in digital transformation tasks related to transport infrastructure. Key directions for future development are outlined, including the integration of fuzzy logic, digital twins, and artificial intelligence modules.
Full Text
##article.viewOnOriginalSite##About the authors
Nikolay A. Zagorodnikh
MIREA – Russian Technological University
Author for correspondence.
Email: zagorodnikh@mirea.ru
ORCID iD: 0009-0001-1092-7518
SPIN-code: 5689-7571
Scopus Author ID: 57572238600
ResearcherId: F-8619-2019
Cand. Sci. (Eng.), Associate Professor, associate professor, Department of Industrial Programming, Institute of Advanced Technologies and Industrial Programming
Russian Federation, MoscowIgor S. Konstantinov
Belgorod State Technological University named after V.G. Shukhov
Email: konstantinovi@mail.ru
ORCID iD: 0000-0002-8903-4690
SPIN-code: 6666-1523
Scopus Author ID: 56426832100
ResearcherId: ABI-6473-2020
Dr. Sci. (Eng.), Professor, Institute of Information Technology and Control Systems
Russian Federation, BelgorodReferences
- Bugaevsky L.M., Tsvetkov V.Ya. Geoinformation systems. Moscow: Zlatoust, 2000. 256 p.
- Zagorodnikh N.A. Information system for identifying traffic accident concentration centers: implementation results and development prospects. Management of Road Safety Activities. 2019. No. 1 (2). Pp. 183–187. (In Rus.)
- Zagorodnikh N.A. Mathematical modeling of road safety for vehicle drivers. Advances in Modern Science. 2015. No. 2. Pp. 31–36. (In Rus.)
- Zagorodnikh N.A. Methods for analyzing traffic accident sites: A comparative review of algorithms. Information Systems and Technologies. 2025. No. 2 (148). Pp. 108–116. (In Rus.)
- Zagorodnikh N.A., Nesov I.S. Analysis of world experience in the implementation and use of geoinformation technologies to ensure road safety. In: Information technologies and innovations in transport: collection of scientific papers of the 5th Int. scientific and practical conf. Orel: Orel State University named after I.S. Turgenev, 2020. Pp. 143–150.
- Zagorodnikh N.A., Novikov A.N. Software implementation of the algorithm for identifying accident-hazardous road sections. Transportation Research Procedia. 2018. No. 36. Pp. 817–825. (In Rus.). doi: 10.1016/j.trpro.2018.12.074.
- Zagorodnikh N.A., Semkin A.N. Main aspects of the universal model of digital transport infrastructure. World of Transport and Technological Machines. 2018. No. 2 (61). Pp. 116–123. (In Rus.)
- Kovalev S.S., Morozov D.D. Application of Getis-Ord Gi* statistics to identify accident hot spots in a metropolis. Urban Research. 2022. Vol. 8. No. 1. Pp. 27–35. (In Rus.)
- Chen H., Xie K., Wang J. A review of traffic crash prediction models using artificial intelligence algorithms. Journal of Advanced Transportation. 2018. No. 2018. Pp. 1–12. doi: 10.1155/2018/9360123.
- Geurts K., Wets G. Data mining for traffic accident analysis and road safety improvement. Transportation Research Record. 2005. No. 1922. Pp. 39–49. doi: 10.3141/1922-05.
- Hossain M., Muromachi Y. A Bayesian network based framework for real-time crash prediction on the urban expressway. Accident Analysis & Prevention. 2012. No. 45. Pp. 373–381. doi: 10.1016/j.aap.2011.08.001.
- Huang H., Abdel-Ati M. Multilevel Bayesian analysis of crash rates at signalized intersections. Transportation Research Record. 2010. No. 2148. Pp. 27–37. doi: 10.3141/2148-04.
- Lee H., Kim S. Identifying hotspots of influenza spread Using Getis-Ord Gi* statistics. Public Health Journal. 2020. No. 15. Pp. 78–85.
- Mitra S., Washington S. On the nature of over-dispersion in motor vehicle crash prediction models. Accident Analysis & Prevention. 2007. Vol. 39. No. 3. Pp. 459–468. doi: 10.1016/j.aap.2006.08.002.
- Molina J.C., Torres J.P., Roca J. Identification of traffic accident hotspots using kernel density estimation and cluster analysis. Transportation Research Procedia. 2020. No. 47. Pp. 167–174. doi: 10.1016/j.trpro.2020.03.081.
- Smith J., Johnson L. Using kernel density estimation for crime hotspot analysis. Journal of Criminal Justice. 2019. No. 47. Pp. 123–130.
- Wang Y., Li X. Machine learning approaches for urban traffic congestion prediction. Transportation Research Record. 2021. No. 2675. Pp. 567–575.
- Xie Z., Yan J. Kernel density estimation of traffic accidents in a network space. Computers, Environment and Urban Systems. 2008. Vol. 32. No. 5. Pp. 396–406. doi: 10.1016/j.compenvurbsys.2008.05.001.
- Zahran M., Kato H. Kernel density estimation for analyzing the spatial patterns of traffic accidents. Journal of Traffic and Transportation Engineering. 2016. No. 3 (4). Pp. 345–352.
Supplementary files
